šļø The Harness Is the Hard Part of Agentic Pentesting šļø
An AppSec team can point an AI agent running on a generalpurpose model at its own web apps with little setup. Sure, the model writes the attacks. But everything that makes those attacks safe to run against production and worth acting on afterward lives in the harness around the model. The harness is where the engineering in AI pentesting sits. The Hugging Face intrusion OpenAI disclosed in July.
š Read more.
š Via "The Hacker News"
----------
šļø Seen on @cibsecurity
An AppSec team can point an AI agent running on a generalpurpose model at its own web apps with little setup. Sure, the model writes the attacks. But everything that makes those attacks safe to run against production and worth acting on afterward lives in the harness around the model. The harness is where the engineering in AI pentesting sits. The Hugging Face intrusion OpenAI disclosed in July.
š Read more.
š Via "The Hacker News"
----------
šļø Seen on @cibsecurity